Choose your default model in the configuration step during onboarding. The setting is stored for your account and applied server-side to every request. After onboarding, your team's Models page in the dashboard — open your team, then go to Models — lets you choose which models the router may route to; it does not change the account default.
You can choose any model from Available Models, or choose auto to let the AI Router decide which model to use.
Set the model parameter when a specific request needs to use a different model from your account default. For example:
Using OpenAI:
Using langchain:
You can also set model to auto to let the AI Router decide for that request.
Per-request parameters override your account configuration. When a request sends routing parameters, the AI Router uses those values for that request instead of your account configuration. Requests that hard-code routing parameters will not pick up later changes you make in the dashboard.
...
client.chat.completions.create(
model='gpt-5.2',
messages=[{"role": "user", "content": input}]
)
llm = ChatOpenAI(
model='gpt-5.2',
base_url='https://api.airouter.io',
)